add GetLevelCount

eda/feededa/src/main/scala/com/gmei/EsmmData.scala

@@ -225,7 +225,6 @@ object EsmmData {
 }
 
 
-
 object EsmmPredData {
 
   Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
@@ -432,7 +431,6 @@ object EsmmPredData {
 
 }
 
-
 object GetDiaryPortrait {
 
   Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
@@ -604,3 +602,64 @@ object GetDevicePortrait {
   }
 
 }
+
+object GetLevelCount {
+
+  Logger.getLogger("org.apache.spark").setLevel(Level.WARN)
+  Logger.getLogger("org.apache.eclipse.jetty.server").setLevel(Level.OFF)
+
+  case class Params(env: String = "dev",
+                    path: String = null
+                   ) extends AbstractParams[Params] with Serializable
+
+  val defaultParams = Params()
+
+  val parser = new OptionParser[Params]("Feed_EDA") {
+    head("EsmmData")
+    opt[String]("env")
+      .text(s"the databases environment you used")
+      .action((x, c) => c.copy(env = x))
+    opt[String]("path")
+      .text(s"the path you used")
+      .action((x,c) => c.copy(path = x))
+    note(
+      """
+        |For example, the following command runs this app on a tidb dataset:
+        |
+        | spark-submit --class com.gmei.EsmmData ./target/scala-2.11/feededa-assembly-0.1.jar \
+      """.stripMargin +
+        s"|   --env ${defaultParams.env}"
+    )
+  }
+
+
+
+  def main(args: Array[String]): Unit = {
+    parser.parse(args, defaultParams).map { param =>
+      GmeiConfig.setup(param.env)
+      val spark_env = GmeiConfig.getSparkSession()
+      val sc = spark_env._2
+
+      val ti = new TiContext(sc)
+      ti.tidbMapTable(dbName = "jerry_prod",tableName = "data_feed_click")
+      ti.tidbMapTable(dbName = "jerry_prod",tableName = "diary_feat")
+
+      val diary_queue = sc.read.json(param.path)
+      val diary_level1 = sc.sql(
+        s"""
+           |select diary_id,explode(split(level1_ids,';')) from diary_feat
+           |where diary_id in "${diary_queue}"
+         """.stripMargin
+      )
+      diary_level1.show()
+      println(diary_level1.count())
+
+      val level1_count = diary_level1.rdd.map(x => (x(1).toString)).map(level1 => (level1,1)).reduceByKey((a,b) => a+b)
+      level1_count.collect()
+
+      sc.stop()
+
+    }
+  }
+
+}
\ No newline at end of file